跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20569 · v1

ToolGraph as a Q-Function for Test-Time Scaling of Tool-Use Agents

首次提交 2026-11-16 13:50
版本更新 2026-11-16 13:50
雷达观测 2026-11-17 13:07
arXiv ↗PDF ↗

摘要

Tool-use agents must chain interdependent calls, yet which outputs satisfy which later inputs in a deployed catalog is not something a general-purpose language model reliably infers from tool descriptions alone. We compile that structure once into a reusable external representation. ToolGraph is a directed, weighted dependency graph over a tool catalog: parameter matching and interventional probes, which execute a candidate chain with and without its proposed predecessor, propose edges whose evidence is combined into an edge confidence. Prior work uses such graphs to retrieve tools, search for tool paths, or score the next call. We ask instead whether the same structure can supply a \emph{multi-step} value by composing graph paths into a goal-conditioned action value Q(s,a,g)Q(s,a,g). We study three estimators (dynamic programming over entity sets, a GraphSAGE estimator distilled from it, and an LLM scorer conditioned on graph evidence) plus a verbalizer that returns action--goal feedback to the agent, which keeps final action selection. Across two tool-use benchmarks and three backbones, we compare value ranking against personalized-PageRank retrieval over the identical graph, and against direct and reflective agents. Composition pays off only when the estimator also reads the concrete state: the LLM estimator improves on PageRank in every benchmark--backbone setting, by 8.38.3 points on average, while the two purely structural estimators fall below it, because a value defined over tool types cannot separate a correct tool called with a wrong argument. Graph construction is a one-time cost; we report it separately rather than assume it amortized away (at our scale it is comparable to request-time cost) and sweep four knobs controlling how much graph evidence to expose against success and tokens.

作者备注:40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: From Pretrained Representations to Acting Agents (PTA)

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 13:50 · 最新观测版本

ToolGraph as a Q-Function for Test-Time Scaling of Tool-Use Agents

Tool-use agents must chain interdependent calls, yet which outputs satisfy which later inputs in a deployed catalog is not something a general-purpose language model reliably infers from tool descriptions alone. We compile that structure once into a reusable external representation. ToolGraph is a directed, weighted dependency graph over a tool catalog: parameter matching and interventional probes, which execute a candidate chain with and without its proposed predecessor, propose edges whose evidence is combined into an edge confidence. Prior work uses such graphs to retrieve tools, search for tool paths, or score the next call. We ask instead whether the same structure can supply a \emph{multi-step} value by composing graph paths into a goal-conditioned action value Q(s,a,g)Q(s,a,g). We study three estimators (dynamic programming over entity sets, a GraphSAGE estimator distilled from it, and an LLM scorer conditioned on graph evidence) plus a verbalizer that returns action--goal feedback to the agent, which keeps final action selection. Across two tool-use benchmarks and three backbones, we compare value ranking against personalized-PageRank retrieval over the identical graph, and against direct and reflective agents. Composition pays off only when the estimator also reads the concrete state: the LLM estimator improves on PageRank in every benchmark--backbone setting, by 8.38.3 points on average, while the two purely structural estimators fall below it, because a value defined over tool types cannot separate a correct tool called with a wrong argument. Graph construction is a one-time cost; we report it separately rather than assume it amortized away (at our scale it is comparable to request-time cost) and sweep four knobs controlling how much graph evidence to expose against success and tokens.

查看此版本解读 →查看此版本原文 ↗